English

A Separability Foundation for Random Coefficients Logit

Theoretical Economics 2026-05-18 v4

Abstract

We study stochastic choice across decision problems, each represented as a menu of action labels paired with observable outcome vectors. We propose a consistency condition for behavior in decision problems composed of two separable components: choice probabilities must agree with those obtained when each component is considered in isolation. Together with monotonicity and continuity, this separability requirement characterizes the family of random coefficients logit rules.

Keywords

Cite

@article{arxiv.2312.04827,
  title  = {A Separability Foundation for Random Coefficients Logit},
  author = {Fedor Sandomirskiy and Po Hyun Sung and Omer Tamuz and Ben Wincelberg},
  journal= {arXiv preprint arXiv:2312.04827},
  year   = {2026}
}

Comments

46 pages

R2 v1 2026-06-28T13:44:43.665Z